paper-with-me

Papers

SPARC: A Multi-Agent System for Electrical Circuit Question Answering

2026-06-05 · Mushtari Sadia, Zhenning Yang, Umme Habiba Lamia, Nishat Shawrin, Ang Chen, Amrita Roy Chowdhury arxiv

Electrical circuit diagram QA tasks require complex mathematical reasoning, which remains challenging for multimodal LLMs. We present SPARC, a multi-agent system that answers questions over circuit diagrams by grounding reasoning in executable physics-based simulations. SPARC uses LLM agents to synthesize, execute, and analyze simulation programs, improving accuracy and reliability by design. It achieves 83% accuracy, with up to a 58% absolute improvement over baselines, while enabling systematic error diagnosis.

📄 PDF Abstract BibTeX arXiv:2606.20643

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical ReasoningQuestion Answering

Similar Papers 제목 키워드 기반

AITEE -- Agentic Tutor for Electrical Engineering

2025-05-27 · Christopher Knievel, Alexander Bernhardt, Christian Bernhardt

Intelligent tutoring systems combined with large language models offer a promising approach to address students' diverse needs and promote self-efficacious learning. While large language models possess good foundational …

Electrical EngineeringRetrieval-augmented Generation

RESPARC: A Reconfigurable and Energy-Efficient Architecture with Memristive Crossbars for Deep Spiking Neural Networks

2017-02-20 · Aayush Ankit, Abhronil Sengupta, Priyadarshini Panda, Kaushik Roy

Neuromorphic computing using post-CMOS technologies is gaining immense popularity due to its promising abilities to address the memory and power bottlenecks in von-Neumann computing systems. In this paper, we propose RES…

2D Object Detection2k

SPARC: Prediction-Based Safe Control for Coupled Controllable and Uncontrollable Agents with Conformal Predictions

2024-10-21 · Shuqi Wang, Siqi Wang, ShaoYuan Li, Xiang Yin

We investigate the problem of safe control synthesis for systems operating in environments with uncontrollable agents whose dynamics are unknown but coupled with those of the controlled system. This scenario naturally ar…

Autonomous DrivingConformal PredictionPrediction

SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs

2026-02-06 · Niccolo Avogaro, Nayanika Debnath, Li Mi, Thomas Frick 외 arxiv

Despite recent successes, test-time scaling -- i.e., dynamically expanding the token budget during inference as needed -- remains brittle for vision-language models (VLMs). Unstructured visual reasoning chains entangle p…

Reinforcement LearningVisual Reasoning

KCLNet: Electrically Equivalence-Oriented Graph Representation Learning for Analog Circuits

2026-03-25 · Peng Xu, Yapeng Li, Tinghuan Chen, Tsung-Yi Ho 외 arxiv

Digital circuits representation learning has made remarkable progress in the electronic design automation domain, effectively supporting critical tasks such as testability analysis and logic reasoning. However, represent…

Graph Representation LearningGraph Neural Network